How to Use the Kiwify MCP in Vercel AI SDK

Build real-time Kiwify sales dashboards that stream live data into your React frontends with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kiwify MCP to Vercel AI SDK

Create your Vinkius account to connect Kiwify to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kiwify with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Sales and Subscription Data

This tool lets your agent pull recent sales and display them instantly. Your code calls `list_sales_history` to get the latest transactions, then uses `get_sale_details` to fetch the specifics for each one. With the Vercel AI SDK, this data streams directly into your UI components as it arrives, not after a loading spinner. It works the same way for subscriptions. You can build a live MRR counter or an updating list of active customers using `list_active_subscriptions`. Since the data appears as the agent gets it, you can create reactive, user-facing dashboards that feel alive and connected to your Kiwify store.

Manage Webhooks from Your Vercel AI SDK App

Build an internal settings panel where your team can manage integrations without bugging developers. Your agent can use `list_configured_webhooks` to show what's already set up. When a new service needs sales alerts, the agent simply calls `create_notification_webhook` with the new URL. Cleaning up is just as easy. If an old analytics service is shut down, the agent can call `delete_notification_webhook` to remove the dead endpoint. This MCP Server gives you the tools to build simple, self-service UIs for managing your Kiwify integration points.

Display Product and Account Info On-Demand

This lets your agent pull product information directly into your app. Your UI can use `list_products` to populate a full catalog or `get_product_details` to drill down into a specific course or ebook. A user could just ask, "show me the stats for my new course," and the info streams right in. For a quick, high-level view, `get_account_summary` gives you the top-line numbers. It’s a fast way to build a “today’s snapshot” component in a dashboard. You’re connecting your frontend directly to your Kiwify backend data, without writing a separate API.

Setup guide

Set up Kiwify MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Kiwify tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Kiwify transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kiwify. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kiwify now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kiwify MCP in Vercel AI SDK

You connect it through this MCP Server. Your Vercel AI SDK app calls our single endpoint, and we handle the connection and authentication to the Kiwify API securely. You just use the tools in your `generateText` or `streamText` calls.

Yes, that's exactly what this is for. Your agent can use the `list_sales_history` tool, and the AI SDK's streaming capabilities will let you render each sale in your UI as it's fetched. It's perfect for live activity feeds.

It is. Your app uses a single Vinkius token to talk to the MCP Server. Your actual Kiwify API keys are stored securely on our end, never exposed to the client-side or your frontend code.

The tools let your AI client manage your Kiwify store. You can list products, check sales history, get details on specific sales or products, and manage your notification webhooks.

The server only accesses your Kiwify sales, product, subscription, and account summary data. All connections are ephemeral and run in a V8 sandbox, meaning your data is only processed for the duration of the request and never stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript